Jul 2026· International Conference on Smart Communications and Networking· pp. 1-6· 0 citations· 21 references
Abstract
In this paper, we propose a FL4MDS, a Federated Learning-based Misbehavior Detection System (MDS) for connected vehicular networks that identifies malicious and falsified messages without requiring centralized data collection. Using the VeReMi dataset, we demonstrate that a GRU-based temporal model can effectively learn sequential patterns associated with vehicular misbehavior. To address practical challenges in vehicular environments such as non-IID data distributions, intermittent connectivity, and client dropout, we extend FedProxWithSave with a checkpoint-aware federated strategy that combines the stability of FedProx with periodic model state preservation. This design enables robust training under unreliable communication conditions and allows rapid recovery from client or server interruptions. Experimental results indicate that the proposed approach maintains stable detection performance under simulated client dropout, achieving accuracy and ROC-AUC values above 96%, while providing low detection latency and high throughput. These results highlight the effectiveness and resilience of checkpoint-enabled federated learning for scalable misbehavior detection with respect to federated client participation in connected vehicle systems.
FLAIR is introduced, a novel, fully decentralized FL protocol that integrates dynamic, resource-aware secure and self-organized clustering with in-cluster model training, presenting a robust and high performing solution for large-scale, heterogeneous IoT systems.
The findings support federated learning as a viable and communication-efficient direction for privacy-aware intrusion detection in distributed edge-security settings, while also highlighting the need for cautious interpretation, native V2X validation, and future robustness analysis against compromised federated clients.
A framework for DT-VANET is constructed, along with two algorithms designed for cloud server model updates and intra-cluster federated transfer learning, to improve the accuracy of the global model and a data quality score-based mechanism to prevent the global model from being affected by malicious vehicles is developed.
Qasim Zia, Saide Zhu, Haoxin Wang et al.· 0 citations
The results show a success in implementing a real time, scalable, privacy-preserving, and adaptive IDS in large-scale IoT deployments through intelligent workload distribution between edge and cloud layers.
Chidera Winifred John, Eduediuyai Ekerete Dan, P. Asuquo et al.· E3S Web of Conferences· 0 citations
The Internet of Vehicles (IoV) supports essential intelligent transportation applications but encounters challenges in federated learning (FL) due to non-independent and identically distributed (non-IID) data, vehicle mobility, resource heterogeneity, and strict privacy requirements in latency-sensitive scenarios such as misbehavior detection and accident response. Traditional FL methods, such as random client selection and standard FedAvg, often experience slow convergence and reduced performance under non-IID conditions. We introduce a hierarchical federated learning framework for software-defined vehicular fog computing. The framework incorporates FedNova (a normalized-averaging aggregation method for heterogeneous federated optimization) to produce normalized model updates under data heterogeneity, a Reward-Based Payoff Strategy (RBPS) for incentive-aware client selection, and game-theoretic vehicle-aggregator matching based on the college admissions problem. Privacy is strengthened through quantum key distribution (QKD)-assisted secure key establishment and classical gradient masking, with quantum circuit simulation used to assess future enhancements. The three-layer architecture includes vehicles, Roadside Unit (RSU)/ Base Station (BS)-level aggregators, and a Software-Defined Network Controller (SDNC) global aggregator. The framework uses both monetary and service-based incentives, such as toll exemptions, to encourage vehicle participation. Hybrid simulations using OMNeT++, Veins, SUMO, and the VeReMi misbehavior detection dataset show that the proposed approach achieves 94.8% classification accuracy [95% Confidence Interval (CI): 92.7–97.0 over 10 runs], converges in 120 rounds (33% faster than FedAvg), and reduces average latency by 29% (320 ms compared to 450 ms for FedAvg), with statistically significant improvements (p < 0.05). These gains enable faster model adaptation to evolving attacks (5–10 min shorter training cycles) and support real-time safety applications where delays above 400 ms can compromise road safety. Ablation studies confirm the complementary roles of FedNova, RBPS, and matching. Although quantum operations are currently simulated classically, the design remains compatible with future quantum hardware.
Devendra Singh, Dhami, Ngnassi Djami et al.· Frontiers in Artificial Inte...· 0 citations
